{"as_of":"2026-08-09T18:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:344545d8203f52a5f6210ff63ca5da61764c4669da8945c5606ca9ffa5783af7","coverage":[{"denominator":5,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T11:21:40.997661Z","state":"measured"},{"denominator":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.15841/citation-record","integrity":"/paper/2606.15841/integrity","json":"/paper/2606.15841/citation-record.json","paper":"/paper/2606.15841"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.02725","last_updated":"2024-10-03T17:47:29Z","snapshot_observed_at":"2026-08-07T06:52:26.132351Z","submitted_at":"2024-10-03T17:47:29Z","title":"Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02725","snapshot_observed_at":"2026-08-02T11:21:40.881716Z","title":"InInternational Conference on Learning Representations, volume 2024, pages 39578–39601","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.15841","last_updated":"2026-07-20T13:29:49Z","snapshot_observed_at":"2026-08-06T11:26:48.440444Z","submitted_at":"2026-06-14T14:45:57Z","title":"Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T11:21:40.881716Z"},"links":{"cited_paper":"/paper/2410.02725","citing_paper":"/paper/2606.15841"},"observation_digest":"sha256:264cae0d73c6d33d0269f467ef2d341a4d2b6cfe9977c3d8309e574547d29ff2","observation_id":"bce4c447-23a7-4c53-a44f-59c1c57e0f2b","resolution":{"observed_at":"2026-08-02T11:21:40.881716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:21:40.604578Z","title":"Santiago Balseiro, Haihao Lu, and Vahab Mirrokni","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.15841","last_updated":"2026-07-20T13:29:49Z","snapshot_observed_at":"2026-08-06T11:26:48.440444Z","submitted_at":"2026-06-14T14:45:57Z","title":"Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains","version":2},"reference_index":1134,"source":"pdf_text","source_observed_at":"2026-08-02T11:21:40.604578Z"},"links":{"citing_paper":"/paper/2606.15841"},"observation_digest":"sha256:6f3254e971500c1205441903757f9c98bbd8b71c3793d4c2d44814b3e6ed6de0","observation_id":"88d02e3e-8f59-4ebd-92b2-8d439a3e145f","resolution":{"observed_at":"2026-08-02T11:21:40.604578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05176","last_updated":"2023-05-09T05:11:02Z","snapshot_observed_at":"2026-07-31T18:33:34.529799Z","submitted_at":"2023-05-09T05:11:02Z","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05176","snapshot_observed_at":"2026-08-02T11:21:40.659447Z","title":"InInternational Conference on Machine Learn- ing, pages 613–628","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.15841","last_updated":"2026-07-20T13:29:49Z","snapshot_observed_at":"2026-08-06T11:26:48.440444Z","submitted_at":"2026-06-14T14:45:57Z","title":"Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-02T11:21:40.659447Z"},"links":{"cited_paper":"/paper/2305.05176","citing_paper":"/paper/2606.15841"},"observation_digest":"sha256:9cc7563632a08b1074fe7ffffcc9991063850b6d3f2c64e32b7d79640f9125f4","observation_id":"1c8ff15f-a78d-458c-ab0f-94ca179b61c6","resolution":{"observed_at":"2026-08-02T11:21:40.659447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18665","last_updated":"2025-02-23T08:50:33Z","snapshot_observed_at":"2026-07-30T15:06:18.011623Z","submitted_at":"2024-06-26T18:10:22Z","title":"RouteLLM: Learning to Route LLMs with Preference Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18665","snapshot_observed_at":"2026-08-02T11:21:40.997661Z","title":"InProceedings of the 40th International Conference on Machine Learning (ICML’23)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.15841","last_updated":"2026-07-20T13:29:49Z","snapshot_observed_at":"2026-08-06T11:26:48.440444Z","submitted_at":"2026-06-14T14:45:57Z","title":"Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T11:21:40.997661Z"},"links":{"cited_paper":"/paper/2406.18665","citing_paper":"/paper/2606.15841"},"observation_digest":"sha256:e2e0850b523990f3cf87dbe6e295241fee45060868b0c84425d97a5745c2b167","observation_id":"d8341b38-459f-49d1-9a48-b68716fef9df","resolution":{"observed_at":"2026-08-02T11:21:40.997661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-02T11:21:40.788022Z","title":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, and 1 others","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.15841","last_updated":"2026-07-20T13:29:49Z","snapshot_observed_at":"2026-08-06T11:26:48.440444Z","submitted_at":"2026-06-14T14:45:57Z","title":"Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T11:21:40.788022Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2606.15841"},"observation_digest":"sha256:6153861f40144b5ac4a758a5029ee6cd0b13c2900b3be99274bcc6cb48fc779c","observation_id":"2d5fd4e8-7552-4d33-b159-761e1d1babc5","resolution":{"observed_at":"2026-08-02T11:21:40.788022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.15841","last_updated":"2026-07-20T13:29:49Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-06T11:26:48.440444Z","submitted_at":"2026-06-14T14:45:57Z","title":"Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains"},"reference_resolution":{"displayed":5,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":5},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 5 of 5 outbound references and 0 inbound Pith citation observations for arXiv:2606.15841."}